OpenViking is an agent-native context database that unifies memories, resources, and skills under a virtual filesystem paradigm (viking:// URIs). It provides a three-tier context model (L0 abstract, L1 overview, L2 full content), recursive directory-based retrieval with visualized trajectories, and automatic session memory extraction. The system consists of a FastAPI HTTP server with embedded Rust components (RAGFS filesystem, vector index engine), a Rust CLI (ov), Python SDKs, a React/Vite Web Studio dashboard, and VikingBot - an agent framework with multi-channel support (Telegram, Slack, Feishu, etc.) and MCP integration. It integrates with OpenClaw, Claude Code, Codex, OpenCode, Hermes, and LangChain/LangGraph. The codebase demonstrates strong engineering: clean separation of concerns, async-first design, comprehensive test coverage (unit, integration, e2e), and production-ready deployment artifacts (Docker, Helm, multi-arch builds). Benchmarks show significant improvements over baseline agents on LoCoMo (82% vs 24-57% accuracy), tau2-bench (+6-12pp), and HotpotQA (91% at top-20).

volc-sdk-python is the official Volcengine SDK for Python, a programmatic client library for Volcengine cloud services. It is not a standalone application: it exposes service classes that wrap REST APIs and protobuf-defined services. The dominant architecture is a base Service class that handles credential resolution (AK/SK, environment variables, ~/.volc/config), request signing, and HTTP dispatch, while each service defines an api_info mapping from action names to HTTP method/path/query. Some services (TLS, Live) use protobuf-generated models; others use legacy ApiInfo-style raw dicts, creating inconsistent implementation styles across the SDK.